{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.12"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"papermill":{"default_parameters":{},"duration":164.844901,"end_time":"2025-02-02T02:29:36.455841","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2025-02-02T02:26:51.610940","version":"2.6.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"id":"e04ac4cb","cell_type":"markdown","source":"- Metric: Accuracy \n- Features: Tabular (not season) + Actigraphy(max, min, mean, std, sum)\n- Link: https://www.kaggle.com/code/nguynanhvdct122c4/fullfeature\n- private: 0.402, public: 0.354\n- impute missing value: mean\n","metadata":{}},{"id":"cbfdce27","cell_type":"code","source":"import re\nfrom sklearn.base import clone\nfrom sklearn.metrics import cohen_kappa_score\nfrom sklearn.model_selection import StratifiedKFold\nfrom scipy.optimize import minimize\nfrom concurrent.futures import ThreadPoolExecutor\nfrom tqdm import tqdm\nimport polars as pl\nimport polars.selectors as cs\nimport matplotlib.pyplot as plt\nfrom matplotlib.ticker import MaxNLocator, FormatStrFormatter, PercentFormatter\nimport seaborn as sns\nimport os\nfrom sklearn.preprocessing import StandardScaler\nimport matplotlib.pyplot as plt\nfrom keras.models import Model\nfrom keras.layers import Input, Dense\nfrom keras.optimizers import Adam\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport pandas as pd\nfrom colorama import Fore, Style\nfrom IPython.display import clear_output\nimport warnings\nfrom lightgbm import LGBMRegressor\nfrom xgboost import XGBRegressor\nfrom catboost import CatBoostRegressor\nfrom sklearn.ensemble import VotingRegressor, RandomForestRegressor, GradientBoostingRegressor\nfrom sklearn.impute import SimpleImputer, KNNImputer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.compose import ColumnTransformer","metadata":{"execution":{"iopub.execute_input":"2025-02-02T02:26:53.900165Z","iopub.status.busy":"2025-02-02T02:26:53.899811Z","iopub.status.idle":"2025-02-02T02:27:10.143753Z","shell.execute_reply":"2025-02-02T02:27:10.143049Z"},"papermill":{"duration":16.249807,"end_time":"2025-02-02T02:27:10.145581","exception":false,"start_time":"2025-02-02T02:26:53.895774","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"3e6adbdd","cell_type":"markdown","source":"2.Load and Explore Data","metadata":{"papermill":{"duration":0.002933,"end_time":"2025-02-02T02:27:10.152308","exception":false,"start_time":"2025-02-02T02:27:10.149375","status":"completed"},"tags":[]}},{"id":"e6fbf9de","cell_type":"code","source":"def process_file(filename, dirname):\n    \"\"\"Process a single parquet file and extract features\"\"\"\n    df = pd.read_parquet(os.path.join(dirname, filename, 'part-0.parquet'))\n    \n    # Drop 'step' column if it exists\n    if 'step' in df.columns:\n        df.drop('step', axis=1, inplace=True)\n    \n    # Initialize dictionary to store features\n    features = {}\n    \n    # Extract basic statistics for each column\n    for col in df.columns:\n        features[f\"{col}_mean\"] = df[col].mean()\n        features[f\"{col}_std\"] = df[col].std()\n        features[f\"{col}_min\"] = df[col].min()\n        features[f\"{col}_max\"] = df[col].max()\n        features[f\"{col}_sum\"] = df[col].sum()\n    \n    return features, filename.split('=')[1]\n\ndef load_data_parquet(dirname) -> pd.DataFrame:\n    \"\"\"Load and process time series data from directory in parallel\"\"\"\n    ids = os.listdir(dirname)\n    \n    with ThreadPoolExecutor() as executor:\n        results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n    \n    features_list, indexes = zip(*results)\n    \n    # Create DataFrame with extracted features and IDs\n    df = pd.DataFrame(features_list)\n    df['id'] = indexes\n    \n    return df","metadata":{"execution":{"iopub.execute_input":"2025-02-02T02:27:10.159978Z","iopub.status.busy":"2025-02-02T02:27:10.159314Z","iopub.status.idle":"2025-02-02T02:27:10.165824Z","shell.execute_reply":"2025-02-02T02:27:10.165160Z"},"papermill":{"duration":0.011571,"end_time":"2025-02-02T02:27:10.167089","exception":false,"start_time":"2025-02-02T02:27:10.155518","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"efe61355","cell_type":"code","source":"from sklearn.preprocessing import OneHotEncoder\ntrain = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\nfeaturesCols = ['Basic_Demos-Enroll_Season', 'Basic_Demos-Age', 'Basic_Demos-Sex',\n                'CGAS-Season', 'CGAS-CGAS_Score', 'Physical-Season', 'Physical-BMI',\n                'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n                'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n                'Fitness_Endurance-Season', 'Fitness_Endurance-Max_Stage',\n                'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n                'FGC-Season', 'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n                'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n                'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n                'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone', 'BIA-Season',\n                'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n                'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n                'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n                'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n                'BIA-BIA_TBW', 'PAQ_A-Season', 'PAQ_A-PAQ_A_Total', 'PAQ_C-Season',\n                'PAQ_C-PAQ_C_Total', 'SDS-Season', 'SDS-SDS_Total_Raw',\n                'SDS-SDS_Total_T', 'PreInt_EduHx-Season',\n                'PreInt_EduHx-computerinternet_hoursday','sii']\n\ncat_c = ['Basic_Demos-Enroll_Season', 'CGAS-Season', 'Physical-Season', \n          'Fitness_Endurance-Season', 'FGC-Season', 'BIA-Season', \n          'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']\n\ntrain_ts = load_data_parquet(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_data_parquet(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\n\ntime_series_cols = train_ts.columns.tolist()\ntime_series_cols.remove(\"id\")\n\ntrain = pd.merge(train, train_ts, how=\"left\", on='id')\ntest = pd.merge(test, test_ts, how=\"left\", on='id')\n\n\nfeaturesCols += time_series_cols\n\ntrain_df = train[featuresCols]","metadata":{"execution":{"iopub.execute_input":"2025-02-02T02:27:10.174700Z","iopub.status.busy":"2025-02-02T02:27:10.174449Z","iopub.status.idle":"2025-02-02T02:27:52.875325Z","shell.execute_reply":"2025-02-02T02:27:52.874326Z"},"papermill":{"duration":42.706319,"end_time":"2025-02-02T02:27:52.876753","exception":false,"start_time":"2025-02-02T02:27:10.170434","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"adef10e4","cell_type":"markdown","source":"3.Data Preprocessing","metadata":{"papermill":{"duration":0.011559,"end_time":"2025-02-02T02:27:52.900314","exception":false,"start_time":"2025-02-02T02:27:52.888755","status":"completed"},"tags":[]}},{"id":"2948da4f","cell_type":"markdown","source":"5.Feature Engineering","metadata":{"papermill":{"duration":0.011255,"end_time":"2025-02-02T02:27:52.923387","exception":false,"start_time":"2025-02-02T02:27:52.912132","status":"completed"},"tags":[]}},{"id":"dd35ba3c","cell_type":"code","source":"# Loại bỏ các feature liên quan đến \"season\"\nfiltered_features = [feature for feature in featuresCols if feature not in cat_c and feature != 'sii']\n\n# Loại bỏ các hàng có giá trị NaN trong y\ntrain_df = train_df[featuresCols].dropna(subset=['sii'])\n\n# Chuẩn bị dữ liệu X và y\nX = train_df[filtered_features]\ny = train_df['sii']\n\n# Định nghĩa pipeline xử lý dữ liệu số\nnum_transformer = Pipeline(steps=[\n    ('imputer', KNNImputer(n_neighbors=3)),\n    ('scaler', StandardScaler())\n])\n\n# Định nghĩa ColumnTransformer để áp dụng pipeline cho các cột số\npreprocessor = ColumnTransformer(transformers=[\n    ('num', num_transformer, filtered_features)\n])\n\n# Fit và transform X\npreprocessor.fit(X)\nX_transformed = pd.DataFrame(preprocessor.transform(X), columns=filtered_features)\n\n# Kiểm tra các dòng đầu tiên của dữ liệu đã transform\nprint(\"Transformed X DataFrame:\")\nprint(X_transformed.head())","metadata":{"execution":{"iopub.execute_input":"2025-02-02T02:27:52.947459Z","iopub.status.busy":"2025-02-02T02:27:52.947125Z","iopub.status.idle":"2025-02-02T02:27:53.003375Z","shell.execute_reply":"2025-02-02T02:27:53.002153Z"},"papermill":{"duration":0.069984,"end_time":"2025-02-02T02:27:53.004709","exception":false,"start_time":"2025-02-02T02:27:52.934725","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"8d38ede8","cell_type":"markdown","source":"6.Split Data into Training and Testing Sets","metadata":{"papermill":{"duration":0.011325,"end_time":"2025-02-02T02:27:53.027532","exception":false,"start_time":"2025-02-02T02:27:53.016207","status":"completed"},"tags":[]}},{"id":"1d442f80","cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_val, y_train, y_val = train_test_split(X_transformed, y, test_size=0.2, random_state=42)","metadata":{"execution":{"iopub.execute_input":"2025-02-02T02:27:53.052323Z","iopub.status.busy":"2025-02-02T02:27:53.051982Z","iopub.status.idle":"2025-02-02T02:27:53.059278Z","shell.execute_reply":"2025-02-02T02:27:53.058560Z"},"papermill":{"duration":0.021142,"end_time":"2025-02-02T02:27:53.060723","exception":false,"start_time":"2025-02-02T02:27:53.039581","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"dee92abf","cell_type":"markdown","source":"7.Build and Train the Model","metadata":{"papermill":{"duration":0.011143,"end_time":"2025-02-02T02:27:53.083335","exception":false,"start_time":"2025-02-02T02:27:53.072192","status":"completed"},"tags":[]}},{"id":"01c2c50e","cell_type":"code","source":"from sklearn.svm import LinearSVC, SVC\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, ExtraTreesClassifier, AdaBoostClassifier\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.tree import DecisionTreeClassifier\nfrom xgboost import XGBClassifier\nfrom sklearn.model_selection import StratifiedKFold, cross_val_score\n\n\n# Random seed\nseed = 2023\n\n# List of models\nmodels = [\n    LinearSVC(max_iter=10000, random_state=seed),\n    SVC(random_state=seed),\n    KNeighborsClassifier(metric='minkowski', p=2),\n    LogisticRegression(solver='liblinear', max_iter=1000),\n    DecisionTreeClassifier(random_state=seed),\n    RandomForestClassifier(random_state=seed),\n    ExtraTreesClassifier(random_state=seed),\n    AdaBoostClassifier(random_state=seed),\n    XGBClassifier(eval_metric='logloss', random_state=seed)    \n]\n\n# Function to generate baseline results\ndef generate_baseline_results(models, X, y, metrics='accuracy', cv=5, plot_results=False):\n    # Define k-fold\n    kfold = StratifiedKFold(n_splits=cv, shuffle=True, random_state=42)\n    entries = []\n    \n    # Loop through each model\n    for model in models:\n        model_name = model.__class__.__name__\n        print(f\"Training: {model_name}\")\n        scores = cross_val_score(model, X, y, scoring=metrics, cv=kfold)\n        # Lưu kết quả của tất cả các mô hình vào entries\n        entries.extend([(model_name, fold_idx, score) for fold_idx, score in enumerate(scores)])\n    \n    # Create DataFrame\n    cv_df = pd.DataFrame(entries, columns=['model_name', 'fold_id', 'accuracy_score'])\n    \n    # Optional: Plot results if specified\n    if plot_results:\n        sns.boxplot(x='model_name', y='accuracy_score', data=cv_df, color='lightblue', showmeans=True)\n        plt.title(\"Boxplot of baseline Model Accuracy using 5-fold cross-validation\")\n        plt.xticks(rotation=45)\n        plt.show()\n    \n    # Summary result\n    mean = cv_df.groupby('model_name')['accuracy_score'].mean()\n    std = cv_df.groupby('model_name')['accuracy_score'].std()\n\n    baseline_results = pd.concat([mean, std], axis=1)\n    baseline_results.columns = ['Mean', 'Standard Deviation']\n\n    # Sort results\n    baseline_results.sort_values(by='Mean', ascending=False, inplace=True)\n\n    return baseline_results\n\n# Chạy hàm và hiển thị kết quả\ncv_results = generate_baseline_results(models, X_transformed, y, metrics='accuracy', cv=5, plot_results=False)\n\n# In toàn bộ kết quả\nprint(cv_results)\n","metadata":{"execution":{"iopub.execute_input":"2025-02-02T02:27:53.107653Z","iopub.status.busy":"2025-02-02T02:27:53.107321Z","iopub.status.idle":"2025-02-02T02:29:31.001027Z","shell.execute_reply":"2025-02-02T02:29:30.999724Z"},"papermill":{"duration":97.907833,"end_time":"2025-02-02T02:29:31.002680","exception":false,"start_time":"2025-02-02T02:27:53.094847","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"7eb16738","cell_type":"markdown","source":"8.Evaluate the Model","metadata":{"papermill":{"duration":0.012752,"end_time":"2025-02-02T02:29:31.029896","exception":false,"start_time":"2025-02-02T02:29:31.017144","status":"completed"},"tags":[]}},{"id":"cf534bdb","cell_type":"code","source":"XGB_Params = {\n    'learning_rate': 0.05,\n    'max_depth': 6,\n    'n_estimators': 200,\n    'subsample': 0.8,\n    'colsample_bytree': 0.8,\n    'reg_alpha': 1,  # Increased from 0.1\n    'reg_lambda': 5,  # Increased from 1\n    'random_state': 2023,\n    'tree_method': 'gpu_hist',\n}\n\n# Preprocess the test data\nX_test = test[filtered_features]\nX_test = pd.DataFrame(preprocessor.transform(X_test), columns=filtered_features)\n\n# Use the trained model to make predictions\nbest_model = XGBClassifier(eval_metric='logloss', **XGB_Params)\nbest_model.fit(X_train, y_train)\ny_test_pred = best_model.predict(X_test)\n\n# Create a submission DataFrame\nsubmission = pd.DataFrame({\n    'id': test['id'],\n    'sii': y_test_pred\n})\n\n# Save the submission DataFrame to a CSV file\nsubmission.to_csv('submission.csv', index=False)\n\nprint(\"Submission file created successfully.\")  # In ra thông báo khi hoàn thành","metadata":{"execution":{"iopub.execute_input":"2025-02-02T02:29:31.056132Z","iopub.status.busy":"2025-02-02T02:29:31.055782Z","iopub.status.idle":"2025-02-02T02:29:32.878920Z","shell.execute_reply":"2025-02-02T02:29:32.877770Z"},"papermill":{"duration":1.838305,"end_time":"2025-02-02T02:29:32.880682","exception":false,"start_time":"2025-02-02T02:29:31.042377","status":"completed"},"tags":[],"vscode":{"languageId":"r"}},"outputs":[],"execution_count":null},{"id":"49fa303c","cell_type":"markdown","source":"9.Hyperparameter turning","metadata":{"papermill":{"duration":0.012037,"end_time":"2025-02-02T02:29:32.905903","exception":false,"start_time":"2025-02-02T02:29:32.893866","status":"completed"},"tags":[]}},{"id":"45d4f61b","cell_type":"markdown","source":"10.Make Predictions on Test Set","metadata":{"papermill":{"duration":0.012203,"end_time":"2025-02-02T02:29:32.931972","exception":false,"start_time":"2025-02-02T02:29:32.919769","status":"completed"},"tags":[]}},{"id":"6c0020f5","cell_type":"code","source":"","metadata":{"papermill":{"duration":0.012478,"end_time":"2025-02-02T02:29:32.957070","exception":false,"start_time":"2025-02-02T02:29:32.944592","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"bec6609f","cell_type":"markdown","source":"","metadata":{"papermill":{"duration":0.012174,"end_time":"2025-02-02T02:29:32.981772","exception":false,"start_time":"2025-02-02T02:29:32.969598","status":"completed"},"tags":[]}}]}